mcp-firewall

<p align="center"> <h1 align="center">🛡️ MCP Firewall</h1> <p align="center"><strong>The Cloudflare WAF for AI Agents</strong></p> <p align="center">Runtime security proxy for the Model Context Protocol (MCP). Inspect, filter, and block malicious tool calls before they reach your MCP servers.</p> </p>

<p align="center"> <a href="#quick-start">Quick Start</a> · <a href="#features">Features</a> · <a href="#how-it-works">How It Works</a> · <a href="#configuration">Configuration</a> · <a href="#threat-detection">Threat Detection</a> · <a href="#comparison">Comparison</a> · <a href="#roadmap">Roadmap</a> </p>

<p align="center"> </p>

---

> Every protocol gets a firewall. HTTP got WAFs. gRPC got Envoy. MCP gets MCP Firewall.

MCP connects AI agents to real tools — databases, filesystems, APIs, cloud services. But there's no security layer between your agent and those tools:

• 🎣 Tool descriptions can contain prompt injection — a malicious MCP server can hijack your agent
• 🔄 Rug pulls — tool descriptions change after initial approval, bypassing your review
• 💉 Parameter injection — hidden payloads in tool call arguments (base64, shell commands)
• 🕳️ Output poisoning — tool responses inject instructions back into the LLM context
• 📤 Data exfiltration — sensitive data flows to unauthorized external services

# Install
npm install -g mcp-firewall

# Run as a proxy between your MCP client and server
mcp-firewall --config firewall.yaml

# Or try it imme